Skip to main content
World LabsLinkedIn

Worldlabs announces Atlas, an autoregressive model for real-time 3D world generation and exploration.

Source

LinkedInSep 8, 2026
likes
238
comments
8

Post

One more thing… Atlas is an autoregressive model that generates frames one at a time. We’ve optimized a version of Atlas that generates in real-time, allowing you to interactively explore worlds that are generated on-the-fly. Atlas maintains 3D consistency during generation by building up a spatial context of inputs and previously generated frames. You can explore reconstructions of real-world scenes by adding real-world images to the spatial context. To learn more about Atlas and sign up for early access, check out: https://lnkd.in/gUTxh4Xb

linkedin.com/posts/world-labs_one-more-thing-atlas-is-an-autoregressi...Read the full source

Extracted by Autobound

From the Signal API record
Signal
LinkedIn

What this signalsCompany posts often show what the team is pushing right now.

The full record

From the Signal API record

Topics and mentions

Tags

  • Artificial Intelligence
  • Product Launch

Initiatives

  • developing real-time 3D world generation model
  • offering early access to Atlas model

Technologies named

  • Atlas

Extraction

Detected
Sep 8, 2026
signal_type
linkedin-post-company
signal_subtype
linkedinPost

Use this data

Get every LinkedIn signal for World Labs and the companies you sell to, in the tools you already use.

  1. Ask Claude about it

    Connect Autobound to Claude, Claude Code or Cursor with MCP. Then ask: “What changed at World Labs this week?”

  2. Send it to your own tools

    The Signal API returns LinkedIn signals for any list of companies as JSON, for your CRM, warehouse or app.

  3. Try it free

    Sign up and spend your free credits on the companies you sell to.

    Start Free1,000 free credits

The API returns more than this page shows

This page shows a preview. The full linkedin-post-company record in the Signal API and MCP can also have these 8 fields. Some fields are empty for some signals.

Company

  • linkedin_urlValue in the API
  • industriesValue in the API
  • employee_count_lowValue in the API
  • employee_count_highValue in the API
  • revenueValue in the API
  • descriptionValue in the API

Signal

  • signal_nameValue in the API
  • associationValue in the API
Show the full JSONThe record on this page and the API request

GET /v1/signals/44318833-9443-4fd3-b68b-dea362e053a0 returns this record as JSON. POST /v1/companies/enrich returns every signal for worldlabs.ai.

{
  "signal_id": "44318833-9443-4fd3-b68b-dea362e053a0",
  "signal_type": "linkedin-post-company",
  "signal_subtype": "linkedinPost",
  "detected_at": "2026-09-08T18:50:09.521+00:00",
  "company": {
    "name": "World Labs",
    "domain": "worldlabs.ai"
  },
  "data": {
    "tags": [
      "Artificial Intelligence",
      "Product Launch"
    ],
    "summary": "Worldlabs announces Atlas, an autoregressive model for real-time 3D world generation and exploration.",
    "post_url": "https://www.linkedin.com/posts/world-labs_one-more-thing-atlas-is-an-autoregressive-activity-7503162783128006656-ZAR4",
    "num_likes": 238,
    "post_text": "One more thing…\n\nAtlas is an autoregressive model that generates frames one at a time. We’ve optimized a version of Atlas that generates in real-time, allowing you to interactively explore worlds that are generated on-the-fly.\n\nAtlas maintains 3D consistency during generation by building up a spatial context of inputs and previously generated frames.\n\nYou can explore reconstructions of real-world scenes by adding real-world images to the spatial context.\n\nTo learn more about Atlas and sign up for early access, check out:\nhttps://lnkd.in/gUTxh4Xb",
    "initiatives": [
      {
        "topic": "developing real-time 3D world generation model",
        "urgency": 0.7
      },
      {
        "topic": "offering early access to Atlas model",
        "urgency": 0.6
      }
    ],
    "posted_date": "2026-09-08T18:50:09.521Z",
    "num_comments": 8,
    "technologies_mentioned": [
      {
        "name": "Atlas",
        "status": "using"
      }
    ]
  }
}

Long text fields are shortened on this page.

Looking up one signal by its id is free. Enrich costs 2 credits per signal returned; a call with no results is free.